{"id":"https://openalex.org/W4415164137","doi":"https://doi.org/10.48550/arxiv.2504.15457","title":"Improving Human-AI Coordination through Online Adversarial Training and Generative Models","display_name":"Improving Human-AI Coordination through Online Adversarial Training and Generative Models","publication_year":2025,"publication_date":"2025-04-21","ids":{"openalex":"https://openalex.org/W4415164137","doi":"https://doi.org/10.48550/arxiv.2504.15457"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2504.15457","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15457","pdf_url":"https://arxiv.org/pdf/2504.15457","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.15457","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056077938","display_name":"Paresh Chaudhary","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaudhary, Paresh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036275688","display_name":"Yancheng Liang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Yancheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083838185","display_name":"Daphne Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Daphne","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033061754","display_name":"Simon S. Du","orcid":"https://orcid.org/0000-0003-0056-8299","observed_orcids":["https://orcid.org/0000-0003-0056-8299"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Simon S.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046953322","display_name":"Natasha Jaques","orcid":"https://orcid.org/0000-0002-8413-9469","observed_orcids":["https://orcid.org/0000-0002-8413-9469"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jaques, Natasha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9487000107765198,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.03880000114440918,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.002199999988079071,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/human-ai-coordination","display_name":"human-AI coordination","score":0.9380000233650208},{"id":"https://openalex.org/keywords/adversarial-training","display_name":"adversarial training","score":0.8510000109672546},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.925000011920929},{"id":"https://openalex.org/keywords/cooperative-agents","display_name":"cooperative agents","score":0.39899998903274536},{"id":"https://openalex.org/keywords/human-robot-interaction","display_name":"human-robot interaction","score":0.5830000042915344}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.9085000157356262},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.7476999759674072},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6909999847412109},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6754999756813049},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5922999978065491},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5134000182151794},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5016999840736389},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4462999999523163},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C184408114","wikidata":"https://www.wikidata.org/wiki/Q1502022","display_name":"Generative Design","level":3,"score":0.3050999939441681},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2578999996185303}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2504.15457","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15457","pdf_url":"https://arxiv.org/pdf/2504.15457","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2504.15457","doi":"https://doi.org/10.48550/arxiv.2504.15457","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.15457","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.15457","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.15457","pdf_url":"https://arxiv.org/pdf/2504.15457","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Being":[0],"able":[1],"to":[2,20,25,77,86,110,119,164,209],"cooperate":[3],"with":[4,116,187],"diverse":[5,210],"humans":[6,27],"is":[7,41,84],"an":[8,96],"important":[9],"component":[10],"of":[11,36,68,141,196],"many":[12],"economically":[13],"valuable":[14],"AI":[15],"tasks,":[16],"from":[17],"household":[18],"robotics":[19],"autonomous":[21],"driving.":[22],"However,":[23,81],"generalizing":[24,208],"novel":[26,102],"requires":[28],"training":[29,40,83,118],"on":[30,200],"data":[31,48],"that":[32,45,52,104],"captures":[33],"the":[34,62,66,79,134,138,142,149,152,162,176,192,197,201],"diversity":[35],"human":[37,189,211],"behaviors.":[38,212],"Adversarial":[39,129],"a":[42,58,89,101,106],"promising":[43],"method":[44,125],"allows":[46],"dynamic":[47],"generation":[49,67],"and":[50,191],"ensures":[51],"agents":[53],"are":[54],"robust.":[55],"It":[56],"creates":[57],"feedback":[59],"loop":[60],"where":[61,148],"agent's":[63],"performance":[64,199],"influences":[65],"new":[69],"adversarial":[70,82,97,117,182],"data,":[71],"which":[72],"can":[73,93],"be":[74],"used":[75],"immediately":[76],"train":[78,95],"agent.":[80],"difficult":[85],"apply":[87],"in":[88,207],"cooperative":[90,113],"task;":[91],"how":[92],"we":[94],"cooperator?":[98],"We":[99,122,169,184],"propose":[100],"strategy":[103],"combines":[105],"pretrained":[107],"generative":[108,143,177],"model":[109,144,178],"simulate":[111],"valid":[112],"agent":[114],"policies":[115],"maximize":[120],"regret.":[121],"call":[123],"our":[124],"GOAT:":[126],"Generative":[127],"Online":[128],"Training.":[130],"In":[131],"this":[132],"framework,":[133],"GOAT":[135,156,186],"dynamically":[136],"searches":[137],"latent":[139],"space":[140],"for":[145],"coordination":[146,172],"strategies":[147,173],"learning":[150],"policy,":[151],"Cooperator":[153,163],"agent,":[154],"underperforms.":[155],"enables":[157],"better":[158],"generalization":[159],"by":[160,174],"exposing":[161],"various":[165],"challenging":[166],"interaction":[167],"scenarios.":[168],"maintain":[170],"realistic":[171],"keeping":[175],"frozen,":[179],"thus":[180],"avoiding":[181],"exploitation.":[183],"evaluate":[185],"real":[188],"partners,":[190],"results":[193],"demonstrate":[194],"state":[195],"art":[198],"Overcooked":[202],"benchmark,":[203],"highlighting":[204],"its":[205],"effectiveness":[206]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-14T00:00:00"}